Multi-Perspective Cost-Sensitive Context-Aware Multi-Instance Sparse Coding and Its Application to Sensitive Video Recognition

Abstract

Abstract:With the development of video-sharing websites, P2P, micro-blog, mobile WAP websites, and so on, sensitive videos can be more easily accessed. Effective sensitive video recognition is necessary for web content security. Among web sensitive videos, this paper focuses on violent and horror videos. Based on color emotion and color harmony theories, we extract visual emotional features from videos. A video is viewed as a bag and each shot in the video is represented by a key frame which is treated as an instance in the bag. Then, we combine multi-instance learning (MIL) with sparse coding to recognize violent and horror videos. The resulting MIL-based model can be updated online to adapt to changing web environments. We propose a cost-sensitive context-aware multi-instance sparse coding (MI-SC) method, in which the contextual structure of the key frames is modeled using a graph, and fusion between audio and visual features is carried out by extending the classic sparse coding into cost-sensitive sparse coding. We then propose a multi-perspective multi-instance joint sparse coding (MI-J-SC) method that handles each bag of instances from an independent perspective, a contextual perspective, and a holistic perspective. The experiments demonstrate that the features with an emotional meaning are effective for violent and horror video recognition, and our cost-sensitive context-aware MI-SC and multi-perspective MI-J-SC methods outperform the traditional MIL methods and the traditional SVM and KNN-based methods.Index terms: Cost-sensitive context-aware MI-SC, Multi-perspective MI-J-SC, Horror video recognition, Violent video recognition, and Video emotional feature extraction.

A tribe competition-based genetic algorithm for feature selection in pattern classification

“…Readers are referred to the Discussion Section for more details on parameter settings. We compared the proposed TCbGA algorithm to several state-of-the-art feature selection algorithms, including DEMOFS [34] , MOEA/D [35], MDisABC [36], W-QEISS [37], SB-ELM [38], HPSO-LS [39], MoDE [40], GASNCM [41], GCACO [42], GCNC [43], UFSACO [44], FFW-DGC [45], QIFS [46], FSFWISIW [47], BALO [48], MI-SC [49], VMBACO [50], HDBPSO [51] and bGWO [52]. Table 3 shows the mean and standard deviation of the classification accuracy obtained by applying our algorithm to each dataset 25 times and the performance of other algorithms reported in the literature.…”

Multi-Instance Learning Algorithm Based on LSTM for Chinese Painting Image Classification

“…SVM) to solve the MIL problem, is a very effective MIl algorithm. For example, DD-SVM [18], Multi-Instance Learning via Embedded Instance Selection (MILES) [19], LSA-MIL [20], MI-J-SC [21], EC-SVM [22], MILDM [23] and miFV/miVLAD [24], etc. Unfortunately, few existing feature representation methods are effective to describe the sematic of images (bags), so it is difficult to adapt some well-known SIL methods to solve the MIL problems.…”

Affective Computing for Large-scale Heterogeneous Multimedia Data

“…To represent audio content, pitch, zero crossing rates (ZCR), Mel frequency cepstrum coefficients (MFCC), and energy are the most popular features [2,43,82,132,170]. In particular, the MFCC [14,49,74,147,176,177] and its ∆MFCC are used to characterize emotions in video clips frequently; while the derivatives and statistics (min, max,mean) of MFCC or ∆MFCC are also explored widely. As for pitch, [87] shows that pitch of sound is associated closely with some emotions, such as anger with higher pitch and sadness with lower standard deviation of pitch.…”

“…For example, EmoBase10 feature depicting audio cues is computed in [147]. Hu et al [49] proposed a method of combining the audio and visual features to model contextual structures of the key frames selected from video. This can produce a kind of so-called multiinstance sparse coding (MI-SC) for next analysis.…”